https://doi.org/10.1140/epjp/i2016-16167-6
Regular Article
Application of artificial neural network in precise prediction of cement elements percentages based on the neutron activation analysis
1
Young Researchers and Elite Club, Kermanshah Branch, Islamic Azad University, Kermanshah, Iran
2
Radiation Application Department, Shahid Beheshti University, G. C, I.R Iran
3
Department of Electrical Engineering, Kermanshah University of Technology, Kermanshah, Iran
* e-mail: e.eftekharizade@yahoo.com
Received:
17
December
2015
Revised:
5
April
2016
Accepted:
21
April
2016
Published online:
25
May
2016
Due to variation of neutron energy spectrum in the target sample during the activation process and to peak overlapping caused by the Compton effect with gamma radiations emitted from activated elements, which results in background changes and consequently complex gamma spectrum during the measurement process, quantitative analysis will ultimately be problematic. Since there is no simple analytical correlation between peaks’ counts with elements’ concentrations, an artificial neural network for analyzing spectra can be a helpful tool. This work describes a study on the application of a neural network to determine the percentages of cement elements (mainly Ca, Si, Al, and Fe) using the neutron capture delayed gamma-ray spectra of the substance emitted by the activated nuclei as patterns which were simulated via the Monte Carlo N-particle transport code, version 2.7. The Radial Basis Function (RBF) network is developed with four specific peaks related to Ca, Si, Al and Fe, which were extracted as inputs. The proposed RBF model is developed and trained with MATLAB 7.8 software. To obtain the optimal RBF model, several structures have been constructed and tested. The comparison between simulated and predicted values using the proposed RBF model shows that there is a good agreement between them.
© Società Italiana di Fisica and Springer-Verlag Berlin Heidelberg, 2016